Borrowing it
Nothing to install: this file belongs to tickadoo/tickadoo-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tickadoo/tickadoo-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/tickadoo/tickadoo-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/tickadoo/tickadoo-mcp/claude-md)<a href="https://agentmods.dev/instructions/tickadoo/tickadoo-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tickadoo/tickadoo-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/tickadoo/tickadoo-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tickadoo/tickadoo-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01843 | $0.01843 |
| Opus 5.5 | $0.00737 | $0.00737 |
| Sonnet 5.5 | $0.00369 | $0.00369 |
| Haiku 4.5 | $0.00184 | $0.00184 |
Grade A, and why
tickadoo-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@AGENTS.md
CLAUDE.md — tickadoo-mcp
This file is read automatically by Claude Code at session start. Lightweight project doc; defers to AGENTS.md for the shared AI-agent coordination conventions and to the HowardOS repo (github.com/tickadoo/howard → CLAUDE.md) for the broader tickadoo project context (architecture, deploy workflows, environment variables, supplier integrations, team, Slack IDs, etc.).
What is this repo?
@tickadoo/mcp-server — the npm distribution of the public tickadoo MCP (Model Context Protocol) server. It exposes the live tickadoo experiences catalogue to AI agents (ChatGPT, Claude, Perplexity, etc.) so they can search, browse, recommend, and book on behalf of end users. Installed by clients from the MCP Marketplace / npm, or used directly over Streamable HTTP at https://mcp.tickadoo.com/mcp.
Since v2.0.0 this package is a thin remote bridge (GRO-573): the npm command is a stdio transport that proxies to the canonical remote server. It no longer defines tools, formats catalogue data, or calls a backend directly. The remote owns the tool list, schemas, results, and errors. The remote MCP server (and the embeddable widget bundle) now live in the HowardOS repo (github.com/tickadoo/howard), which is canonical (GRO-574).
The established full remote can expose richer booking and agent-intelligence
metadata. The portable public-plugin surface at
https://mcp.tickadoo.com/mcp/agents is a separate discovery-only contract: it
omits direct transaction links, purchase-oriented fields, renderer/write tools,
coordinate-bearing tools, MCP resources, and Apps/widget metadata.
Architecture at a glance
- Runtime: TypeScript stdio bridge
src/index.ts→src/bridge.ts— local stdio transport (shipped on npm as@tickadoo/mcp-server) that proxiestools/list,tools/call,resources/list,resources/read, andpingto the remote.src/config.ts— bridge config (remote URL viaTICKADOO_MCP_URL, log level viaTICKADOO_LOG_LEVEL).
- Canonical remotes:
https://mcp.tickadoo.com/mcpis the established full surface used by the npm bridge and direct integrations;https://mcp.tickadoo.com/mcp/agentsis the reviewed discovery-only surface used by the portable OpenAI/Codex package. Both are served and deployed from the howard repo, not this one. This repo does not deploy a Cloudflare Worker. - Build:
npm run build→dist/index.js(esbuild bundle for stdio/npm). - Registry metadata:
server.jsonis refreshed from the live remote vianpm run sync:server-json. - Portable skills (
skills/*/SKILL.md): 7 discovery-only workflows for Agent Plugins clients and the OpenAI Plugin Directory —tickadoo-experiencesplusplan-a-trip,family-day-out,tonight-and-last-minute,date-night,compare-before-you-book, andnear-a-landmark. Ground every tool reference inmetadata/public-agent-tools.json; frontmatternamemust match the folder. The repository-development skill at.claude/skills/tickadoo-experiences/SKILL.mdfollows the separate live full/mcptools/listcontract and is intentionally not a mirror. The npm tarball and deterministic OpenAI ZIP validate their exact, distinct closures. - Testing: vitest (
npm test);LIVE=1 npm testruns the optional live integration test against the remote. - No API key required. Customer never sees supplier names; everything is presented as tickadoo.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago Changed · +4 lines · +39 tokens per session 664bc366cf6f
- 1mo ago Changed · -1 lines · +24 tokens per session 201d079c28b7
- 1mo ago Changed · +1 lines · -10 tokens per session 9444bb3d0449
- 2mo ago First seen · 80 lines · 1,790 tokens per session scan A a225e831e1e4
tickadoo-mcp CLAUDE.md is an instructions file published in the GitHub repository tickadoo/tickadoo-mcp (2 stars, last pushed 3d ago), licensed MIT. It adds 1,843 tokens to every session, about $0.0074 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
tickadoo-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tickadoo-mcp CLAUDE.mdtickadoo/tickadoo-mcp | Instructions file | 2 | 3d ago | MIT | A | 1,843 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |